R Notebook

library(tidyverse)
library(tidyr)
library(dplyr)
library(readr)
library(ggplot2)

steam_data <- read.csv(url("https://raw.githubusercontent.com/CaptainBlast096/Intro-to-Data-Science---Final-Project/main/data/steam.csv?token=AURDUTODKXAEQX3HN6XF2DDBCFCQI"))

steam_data

Warning in for (i in seq_along(cenv$extra)) { :
  closing unused connection 3 (https://raw.githubusercontent.com/CaptainBlast096/Intro-to-Data-Science---Final-Project/main/data/steam.csv?token=AURDUTNV5Q6XH2E6BMHB5ADBCCASW)

colnames(steam_data)

 [1] "appid"            "name"             "release_date"     "english"          "developer"        "publisher"        "platforms"       
 [8] "required_age"     "categories"       "genres"           "steamspy_tags"    "achievements"     "positive_ratings" "negative_ratings"
[15] "average_playtime" "median_playtime"  "owners"           "price"           

steam_filtered <- steam_data %>% 
  filter (genres %in% c("Action", "FPS", "Sci-Fi", "Puzzle", "Indie","Strategy", "Racing","RPG", "Casual", "Horror", "Stealth", "Shooter", "Simulation"))
steam_filtered #Don't use

#Lines filter the ammount of row in each genre

Action <- steam_data %>%  filter(str_detect(steamspy_tags, "Action"))
Action

nrow(Action)

[1] 10344

FPS <- steam_data %>%  filter(str_detect(steamspy_tags, "FPS"))
FPS

nrow(FPS)

[1] 405

Shooter <- steam_data %>%  filter(str_detect(steamspy_tags, "Shooter"))
Shooter

nrow(Shooter)

[1] 227

Sci_fi <- steam_data %>%  filter(str_detect(steamspy_tags, "Sci-fi"))
Sci_fi

nrow(Sci_fi) 

[1] 157

Puzzle <- steam_data %>%  filter(str_detect(steamspy_tags, "Puzzle"))
Puzzle

nrow(Puzzle)

[1] 1167

Indie <- steam_data %>%  filter(str_detect(steamspy_tags, "Indie"))
Indie

nrow(Indie)

[1] 16232

Strategy <- steam_data %>%  filter(str_detect(steamspy_tags, "Strategy"))
Strategy

nrow(Strategy)

[1] 4180

Racing <- steam_data %>%  filter(str_detect(steamspy_tags, "Racing"))
Racing

nrow(Racing)

[1] 765

RPG <- steam_data %>%  filter(str_detect(steamspy_tags, "RPG"))
RPG

nrow(RPG)

[1] 2863

Casual <- steam_data %>%  filter(str_detect(steamspy_tags, "Casual"))
Casual

nrow(Casual)

[1] 8205

Horror <- steam_data %>%  filter(str_detect(steamspy_tags, "Horror"))
Horror

nrow(Horror)

[1] 566

Simulation <- steam_data %>%  filter(str_detect(steamspy_tags, "Simulation"))
Simulation

nrow(Simulation)

[1] 3284

 #Genres

Top_Games <- data.frame (Genres = c("Action", "FPS", "Shooter", "Sci-fi", "Puzzle", "Indie", "Strategy", "Racing", "RPG", "Casual", "Horror", "Simulation"), Amount = c(10344,405,227,157,1167,16232,4180,765,2863,8205,566,3284))


#ggplot(Top_Games, aes(x = Genres, y = Ammount_of_games)) + geom_col(fill = "black") 
ggplot(Top_Games, aes(x = Genres, y = Amount, fill = Genres,)) + geom_bar(stat = "identity", width = 0.5) + coord_flip()